© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58976
    Prev
    Next
    INDEX
    Explanations

    material properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĥģ
    -0.09
    lass
    -0.08
    éĩijå±±
    -0.08
    é¢Ĩä¼ļ
    -0.08
    夸
    -0.08
    äºĶåĽĽ
    -0.08
    åī©
    -0.08
    ä¸ĵ
    -0.07
    ç²¾
    -0.07
    æĿIJ
    -0.07
    POSITIVE LOGITS
    è¹Ļ
    0.09
    æĵĢ
    0.09
    å®ķ
    0.09
    产åĮº
    0.09
     ark
    0.08
    éĿĵ
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    èį·
    0.08
     sÃłng
    0.08
    éĥ¨åī¯
    0.08
    Activations Density 0.931%

    No Known Activations